Optimal uncertainty bounds for multivariate kernel regression under bounded noise: A Gaussian process-based dual function
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911712551108608 |
|---|---|
| author | Lahr, Amon Scampicchio, Anna Köhler, Johannes Zeilinger, Melanie N. |
| author_facet | Lahr, Amon Scampicchio, Anna Köhler, Johannes Zeilinger, Melanie N. |
| contents | Non-conservative uncertainty bounds are essential for making reliable predictions about latent functions from noisy data, and thus, a key enabler for safe learning-based control. In this domain, kernel methods such as Gaussian process regression are established techniques, thanks to their inherent uncertainty quantification mechanism. Still, existing bounds either pose strong assumptions on the underlying noise distribution, are conservative, do not directly apply in the multi-output case, or are difficult to integrate into downstream tasks. This paper addresses these limitations by presenting a tight, deterministic bound for multi-output functions in Reproducing Kernel Hilbert Spaces (RKHSs) subject to bounded noise. It is obtained through an unconstrained, duality-based formulation, which shares the same structure as classic Gaussian process confidence bounds, and can thus be straightforwardly integrated into downstream optimization pipelines. We show that the proposed bound generalizes existing results and illustrate its application using an example inspired by quadrotor dynamics learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16481 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Optimal uncertainty bounds for multivariate kernel regression under bounded noise: A Gaussian process-based dual function Lahr, Amon Scampicchio, Anna Köhler, Johannes Zeilinger, Melanie N. Machine Learning Systems and Control Optimization and Control 68T37 (Primary) 46E22, 60G15 (Secondary) G.3 Non-conservative uncertainty bounds are essential for making reliable predictions about latent functions from noisy data, and thus, a key enabler for safe learning-based control. In this domain, kernel methods such as Gaussian process regression are established techniques, thanks to their inherent uncertainty quantification mechanism. Still, existing bounds either pose strong assumptions on the underlying noise distribution, are conservative, do not directly apply in the multi-output case, or are difficult to integrate into downstream tasks. This paper addresses these limitations by presenting a tight, deterministic bound for multi-output functions in Reproducing Kernel Hilbert Spaces (RKHSs) subject to bounded noise. It is obtained through an unconstrained, duality-based formulation, which shares the same structure as classic Gaussian process confidence bounds, and can thus be straightforwardly integrated into downstream optimization pipelines. We show that the proposed bound generalizes existing results and illustrate its application using an example inspired by quadrotor dynamics learning. |
| title | Optimal uncertainty bounds for multivariate kernel regression under bounded noise: A Gaussian process-based dual function |
| topic | Machine Learning Systems and Control Optimization and Control 68T37 (Primary) 46E22, 60G15 (Secondary) G.3 |
| url | https://arxiv.org/abs/2603.16481 |